Search Results for author:
Found 12 papers, 3 papers with code
LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
It comes from the endoscope's light sources and decays with the inverse of the squared distance to the surface.
LightDepth: Single-View Depth Self-Supervision from Illumination Decline
However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained.
ColonMapper: topological mapping and localization for colonoscopy
We propose a topological mapping and localization system able to operate on real human colonoscopies, despite significant shape and illumination changes.
EndoMapper dataset of complete calibrated endoscopy procedures
Computer-assisted systems are becoming broadly used in medicine.
Medical Image Retrieval
Simultaneous Localization and Mapping
Scale-aware direct monocular odometry
Our proposal does not particularize for a concrete neural network, being able to work along with the vast majority of the existing depth prediction solutions.
SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes
Conventional SLAM techniques strongly rely on scene rigidity to solve data association, ignoring dynamic parts of the scene.
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM
We present in this paper DynaSLAM II, a visual SLAM system for stereo and RGB-D configurations that tightly integrates the multi-object tracking capability.
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
Compared with visual odometry systems that only use information from the last few seconds, ORB-SLAM3 is the first system able to reuse in all the algorithm stages all previous information.
Robotics
Inertial-Only Optimization for Visual-Inertial Initialization
We formulate for the first time visual-inertial initialization as an optimal estimation problem, in the sense of maximum-a-posteriori (MAP) estimation.
Robotics
ORBSLAM-Atlas: a robust and accurate multi-map system
We also show the robustness and capability of our system to deal with dynamic scenes, quantitatively in the EuRoC datasets and qualitatively in a densely populated corridor where camera occlusions and tracking losses are frequent.
Fast and Robust Initialization for Visual-Inertial SLAM
Visual-inertial SLAM (VI-SLAM) requires a good initial estimation of the initial velocity, orientation with respect to gravity and gyroscope and accelerometer biases.
Robotics
Real-time Monocular Object SLAM
We present a real-time object-based SLAM system that leverages the largest object database to date.
